R Notebook
library(lmerTest)
library(ggeffects)
library(dplyr)
library(report)package ‘report’ was built under R version 4.0.5library(r2glmm)
library(performance)package ‘performance’ was built under R version 4.0.5
Attaching package: ‘performance’
The following objects are masked from ‘package:sjstats’:
icc, r2library(corrr)
library(broom.mixed)fullTest <- read.csv("../Cleaning/output/fullTest.csv")
fullTrain <- read.csv("../Cleaning/output/fullTrain.csv")
traitsFreqs <- read.csv("../Cleaning/output/traitFreqOverUnder.csv")
traitsFreqs <- rename(traitsFreqs, props = optionChoiceN)
fullTest <- merge(fullTest, traitsFreqs[c("trait","props")], by = "trait")
fullTest$propCorr <- ifelse(fullTest$Estimator=="Underestimator", 1-fullTest$props, fullTest$props)
uSubs <- unique(fullTest$subID)
indDiffs <- fullTest[!duplicated(fullTest$subID),]fullTest$ingChoiceN <- as.factor(fullTest$ingChoiceN)
fullTest$novel <- as.factor(fullTest$novel)
fullTest$selfResp.Z <- scale(fullTest$selfResp)
fullTest$SE.Z <- scale(fullTest$SE)
fullTest$iSE.Z <- scale(fullTest$iSE)
fullTest$oSE.Z <- scale(fullTest$oSE)
fullTest$predicted.Z <- scale(fullTest$predicted)
fullTest$slope.Z <- scale(fullTest$slope)
fullTest$entropy.Z <- scale(fullTest$entropy)
fullTest$WSR.Z <- scale(fullTest$WSR)
fullTest$neighAveOutSE.Z <- scale(fullTest$neighAveOutSE)
fullTest$neighAveAllSE.Z <- scale(fullTest$neighAveAllSE)
fullTest$neighAveInSE.Z <- scale(fullTest$neighAveInSE)fullTest$novel <- as.factor(fullTest$novel)
levels(fullTest$novel) <- list("Trained" = "0", "Held Out" = "1")evalMat <- matrix(nrow=148, ncol=1)
evalMat[,1] <- 1:148
evalMat <- as.data.frame(evalMat)
colnames(evalMat) <- c("Idx")
for(i in uSubs){
eval <- fullTrain$selfResp[fullTrain$subID==i]
cur <- cbind(fullTrain$Idx[fullTrain$subID==i], eval)
colnames(cur) <- c("Idx",paste0("e",i))
evalMat <- merge(evalMat, cur, by = "Idx", all.x = T)
}MDSframe <-
data.frame(Idx=1:148,
MDS=cmdscale(dist(evalMat[2:length(evalMat)]), eig=TRUE, k=3)$points
)
fullTest <-merge(fullTest, MDSframe, by = "Idx")library(ggpubr)
Loading required package: ggplot2
Registered S3 methods overwritten by 'broom':
method from
tidy.glht jtools
tidy.summary.glht jtools
Registered S3 method overwritten by 'data.table':
method from
print.data.table
Registered S3 methods overwritten by 'car':
method from
influence.merMod lme4
cooks.distance.influence.merMod lme4
dfbeta.influence.merMod lme4
dfbetas.influence.merMod lme4evalMat <- matrix(nrow=0, ncol=3)
evalMat[,2] <- 1:148
evalMat <- as.data.frame(evalMat)
colnames(evalMat) <- c("subID","Idx","eval")
for(i in uSubs){
eval <- fullTrain$selfResp[fullTrain$subID==i]
present <- which(!is.na(eval))
Idx=fullTrain$Idx[fullTrain$subID==i]
Idx=Idx[present]
eval=eval[present]
cur <- cbind(subID=i,
Idx = Idx,
MDS=cmdscale(dist(eval), eig=TRUE, k=1)$points)
evalMat <- rbind(evalMat, cur)
}# prop.test(traitsFreqs$optionChoiceN, traitsFreqs$N, p=rep(.5,length(traitsFreqs$N)))
#
# m <- glmer( ingChoiceN ~ trait + ( 1 | subID) , data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
# optCtrl = list(maxfun = 100000)),
# nAGQ = 1)
#
# fullTest$trait <- as.factor(fullTest$trait)
# contrasts(fullTest$trait) <- contr.sum(148)
# m <- glm(optionChoiceN ~ trait, family = binomial,
# data = fullTest
# )
# summary(m)# traitsFreqs$trait <- as.factor(traitsFreqs$trait)
# contrasts(traitsFreqs$trait) <- contr.sum(148)
# m <- glm(optionChoiceN ~ 1, family = binomial,
# data = traitsFreqs
# )
# summary(m)
# check_overdispersion(m)
# check_model(m)
#
# m <- glm(optionChoiceN ~ trait, family = quasibinomial,
# data = traitsFreqs
# )
# check_overdispersion(m)
# check_model(m)
#
# t.test()
#
# m <- glm(optionChoiceN ~ trait, family = poisson,
# data = traitsFreqs
# )
# check_overdispersion(m)
# check_model(m)propMatrix <- matrix(nrow=148,ncol=7)
for(i in 1:148){
traitDf <- subset(fullTest, Idx==i)
test <- t.test(as.numeric(traitDf$ingChoiceN)-1, mu=.50)
propMatrix[i, ] <- c(i, test$statistic, test$p.value, test$conf.int, test$estimate, test$parameter)
}
colnames(propMatrix) <- c("Idx", "stat", "p", "LCI", "UCI", "est", "param")
propMatrix <- as.data.frame(propMatrix)
propMatrix$trait <- traitsFreqs$trait
propMatrix <- propMatrix[order(propMatrix$p),]x <- indDiffs %>%
select(groupHomoph, seHomoph, DS:SING.Inter) %>%
correlate() %>%
focus(groupHomoph) %>%
arrange(groupHomoph)
x %>%
mutate(rowname = factor(rowname, levels = rowname[order(groupHomoph)])) %>% # Order by correlation strength
ggplot(aes(x = rowname, y = groupHomoph)) +
geom_bar(stat = "identity") +
ylab("Correlation Coefficient") +
xlab("Individual Differences") + theme_grey(base_size = 9) + theme(axis.text.x = element_text(angle = 90,hjust = 1)) +
theme(axis.text.x = element_text(
size = 9, angle = 45, vjust = 1)) + theme(axis.title.x = element_text(vjust=1.9)) + theme(axis.text=element_text(size=9),
axis.title=element_text(size=9,face="bold")) + theme(legend.text = element_text(size=9)) + theme(panel.border = element_rect(colour = "black", fill = NA, size =1)) + theme(legend.title = element_blank()) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"))Familiarity predicts Reaction Time
m <- lmer( log(RT) ~ fam + ( fam | subID) + ( 1 | trait), data = fullTest)boundary (singular) fit: see help('isSingular')summary(m)Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
Formula: log(RT) ~ fam + (fam | subID) + (1 | trait)
Data: fullTest
REML criterion at convergence: 17308.9
Scaled residuals:
Min 1Q Median 3Q Max
-8.2343 -0.5104 -0.0991 0.4294 7.7147
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 3.815e-03 0.061765
subID (Intercept) 6.007e-01 0.775047
fam 1.576e-07 0.000397 1.00
Residual 8.561e-01 0.925263
Number of obs: 6364, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error df t value Pr(>|t|)
(Intercept) 4.215e-02 1.320e-01 4.521e+01 0.319 0.75098
fam 7.134e-03 2.574e-03 1.535e+02 2.771 0.00627 **
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr)
fam -0.414
optimizer (nloptwrap) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("fam")) %>% plot()Model has log-transformed response. Back-transforming predictions to original response scale. Standard errors are still on the log-scale.
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")m <- lmer( log(RT) ~ fam + propCorr + desirability + ( fam | subID) + ( 1 | trait), data = fullTest)boundary (singular) fit: see help('isSingular')
Model failed to converge with 1 negative eigenvalue: -2.4e+03summary(m)Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
Formula: log(RT) ~ fam + propCorr + desirability + (fam | subID) + (1 | trait)
Data: fullTest
REML criterion at convergence: 17319
Scaled residuals:
Min 1Q Median 3Q Max
-8.2458 -0.5121 -0.0995 0.4323 7.7059
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 1.993e-06 0.0014116
subID (Intercept) 5.231e-01 0.7232289
fam 9.680e-07 0.0009839 1.00
Residual 8.607e-01 0.9277194
Number of obs: 6364, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error df t value Pr(>|t|)
(Intercept) 4.221e-02 1.910e-01 2.895e+02 0.221 0.82525
fam 7.534e-03 2.602e-03 3.434e+03 2.896 0.00381 **
propCorr 7.677e-02 8.447e-02 6.292e+03 0.909 0.36349
desirability -8.251e-03 2.842e-02 6.316e+03 -0.290 0.77157
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) fam prpCrr
fam 0.068
propCorr -0.206 0.059
desirabilty -0.728 -0.407 -0.041
optimizer (nloptwrap) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("fam")) %>% plot()Model has log-transformed response. Back-transforming predictions to original response scale. Standard errors are still on the log-scale.
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")Replication of prior self-anchoring findings: Self-evaluations predicting ingroup evaluations
No covariates
m <- glmer( ingChoiceN ~ selfResp.Z + ( selfResp.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
boundary (singular) fit: see help('isSingular')m <- glmer( ingChoiceN ~ selfResp.Z + ( selfResp.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ selfResp.Z + (selfResp.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
4927.2 4964.6 -2457.6 4915.2 3761
Scaled residuals:
Min 1Q Median 3Q Max
-2.8028 -1.0018 0.5326 0.8867 2.9204
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 4.556e-16 2.134e-08
subID (Intercept) 3.259e-01 5.709e-01
selfResp.Z 1.153e-01 3.396e-01 0.54
Number of obs: 3767, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.27860 0.09480 2.939 0.00329 **
selfResp.Z 0.26859 0.06597 4.071 4.68e-05 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr)
selfResp.Z 0.397
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')Covariates
m <- glmer( ingChoiceN ~ selfResp.Z + propCorr + desirability + ( selfResp.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ selfResp.Z + propCorr + desirability + (selfResp.Z |
subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
4587.1 4636.9 -2285.5 4571.1 3759
Scaled residuals:
Min 1Q Median 3Q Max
-4.5860 -0.8321 0.4162 0.7678 3.5706
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.00000 0.0000
subID (Intercept) 0.36416 0.6035
selfResp.Z 0.09248 0.3041 0.59
Number of obs: 3767, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -1.76229 0.50643 -3.480 0.000502 ***
selfResp.Z 0.31074 0.06323 4.914 8.91e-07 ***
propCorr 4.91447 0.27981 17.563 < 2e-16 ***
desirability -0.07200 0.08341 -0.863 0.388029
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) slfR.Z prpCrr
selfResp.Z 0.170
propCorr -0.228 0.055
desirabilty -0.941 -0.110 -0.047
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')library(broom.mixed)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")r2beta(m)boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular') Effect Rsq upper.CL lower.CL
1 Model 0.094 0.112 0.077
3 propCorr 0.079 0.096 0.064
2 selfResp.Z 0.017 0.026 0.009
4 desirability 0.000 0.002 0.000ggpredict(m, c("selfResp.Z")) %>% plot(show.title=F) + xlab("Self-Descriptiveness") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()
ggsave("~/Documents/UC Riverside/Studies/Self-Anchoring/Figures/SelfProjection.tiff",dpi=600)Saving 7.29 x 4.51 in image
Does similarity-weighted self-evaluation average predict ingroup choices?
No covariates
m <- glmer( ingChoiceN ~ WSR.Z + ( WSR.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
m <- glmer( ingChoiceN ~ WSR.Z + ( WSR.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)
Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ WSR.Z + (WSR.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
8068.6 8109.0 -4028.3 8056.6 6271
Scaled residuals:
Min 1Q Median 3Q Max
-7.6462 -0.9681 0.4215 0.8628 3.6516
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.001153 0.03395
subID (Intercept) 8.455504 2.90783
WSR.Z 10.576742 3.25219 0.41
Number of obs: 6277, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.1783 0.4747 0.376 0.707
WSR.Z 0.8192 0.5337 1.535 0.125
Correlation of Fixed Effects:
(Intr)
WSR.Z 0.352 Covariates
m <- glmer( ingChoiceN ~ WSR.Z + propCorr + desirability + ( WSR.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ WSR.Z + propCorr + desirability + (WSR.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
7581.5 7635.5 -3782.8 7565.5 6269
Scaled residuals:
Min 1Q Median 3Q Max
-8.6664 -0.8183 0.3757 0.7582 3.6929
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.000 0.000
subID (Intercept) 7.667 2.769
WSR.Z 8.146 2.854 0.44
Number of obs: 6277, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -1.63543 0.60244 -2.715 0.00663 **
WSR.Z 1.05658 0.48269 2.189 0.02860 *
propCorr 4.80291 0.22735 21.126 < 2e-16 ***
desirability -0.08427 0.06602 -1.276 0.20178
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) WSR.Z prpCrr
WSR.Z 0.334
propCorr -0.143 0.036
desirabilty -0.628 -0.095 -0.060
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")r2beta(m)boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular') Effect Rsq upper.CL lower.CL
1 Model 0.127 0.142 0.113
2 WSR.Z 0.094 0.107 0.081
3 propCorr 0.041 0.051 0.032
4 desirability 0.000 0.001 0.000Does self-evaluation weighted similarity predict ingroup choices?
No covariates
m <- glmer( ingChoiceN ~ SE.Z + ( SE.Z | subID) , data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ SE.Z + (SE.Z | subID)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
8211.1 8244.9 -4100.6 8201.1 6272
Scaled residuals:
Min 1Q Median 3Q Max
-3.0638 -0.9909 0.5065 0.8679 2.7771
Random effects:
Groups Name Variance Std.Dev. Corr
subID (Intercept) 0.36181 0.6015
SE.Z 0.09246 0.3041 0.49
Number of obs: 6277, groups: subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.28008 0.09565 2.928 0.00341 **
SE.Z 0.03742 0.05378 0.696 0.48655
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr)
SE.Z 0.414 Covariates
m <- glmer( ingChoiceN ~ SE.Z + propCorr + desirability + ( SE.Z | subID) , data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ SE.Z + propCorr + desirability + (SE.Z | subID)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
7691.0 7738.2 -3838.5 7677.0 6270
Scaled residuals:
Min 1Q Median 3Q Max
-4.4338 -0.8533 0.4305 0.7844 3.5288
Random effects:
Groups Name Variance Std.Dev. Corr
subID (Intercept) 0.41958 0.6478
SE.Z 0.07936 0.2817 0.57
Number of obs: 6277, groups: subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -1.73776 0.41882 -4.149 3.34e-05 ***
SE.Z 0.07698 0.05304 1.451 0.147
propCorr 4.67962 0.21519 21.746 < 2e-16 ***
desirability -0.05576 0.06869 -0.812 0.417
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) SE.Z prpCrr
SE.Z 0.332
propCorr -0.202 0.034
desirabilty -0.936 -0.243 -0.055tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")r2beta(m) Effect Rsq upper.CL lower.CL
1 Model 0.074 0.087 0.062
3 propCorr 0.073 0.086 0.062
2 SE.Z 0.001 0.003 0.000
4 desirability 0.000 0.001 0.000Do cross-validated similarity*self-evaluation predictions predict ingroup choices?
No covariates
m <- glmer( ingChoiceN ~ predicted.Z + ( predicted.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
boundary (singular) fit: see help('isSingular')m <- glmer( ingChoiceN ~ predicted.Z + ( predicted.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ predicted.Z + (predicted.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
7064.9 7104.4 -3526.4 7052.9 5382
Scaled residuals:
Min 1Q Median 3Q Max
-2.5159 -1.0120 0.6189 0.8789 2.0509
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.0000000 0.00000
subID (Intercept) 0.3092826 0.55613
predicted.Z 0.0004218 0.02054 1.00
Number of obs: 5388, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.31062 0.09159 3.391 0.000696 ***
predicted.Z 0.27783 0.08821 3.149 0.001636 **
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr)
predicted.Z 0.156
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')Covariates
m <- glmer( ingChoiceN ~ predicted.Z + propCorr + desirability + ( predicted.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ predicted.Z + propCorr + desirability + (predicted.Z |
subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
6642.0 6694.8 -3313.0 6626.0 5380
Scaled residuals:
Min 1Q Median 3Q Max
-4.3386 -0.8900 0.4627 0.7848 4.0188
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.0000000 0.00000
subID (Intercept) 0.3575097 0.59792
predicted.Z 0.0002254 0.01501 -1.00
Number of obs: 5388, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -2.12443 0.41091 -5.170 2.34e-07 ***
predicted.Z 0.30607 0.09566 3.199 0.00138 **
propCorr 4.48818 0.22835 19.655 < 2e-16 ***
desirability 0.03223 0.06662 0.484 0.62849
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) prdc.Z prpCrr
predicted.Z 0.073
propCorr -0.246 0.034
desirabilty -0.932 -0.074 -0.032
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")r2beta(m)boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular') Effect Rsq upper.CL lower.CL
1 Model 0.085 0.099 0.071
3 propCorr 0.069 0.083 0.057
2 predicted.Z 0.018 0.025 0.011
4 desirability 0.000 0.001 0.000ggpredict(m, c("predicted.Z")) %>% plot(show.title=F) + xlab("Cross-Validated Self-Descriptiveness Predictions") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()Data were 'prettified'. Consider using `terms="predicted.Z [all]"` to get smooth plots.ggsave("~/Documents/UC Riverside/Studies/Self-Anchoring/Figures/CVprediction.tiff",dpi=600)Saving 7.29 x 4.51 in image
Do people self-anchor more for higher indegree traits?
No covariates
m <- glmer( ingChoiceN ~ predicted.Z * inDegree + ( predicted.Z + inDegree | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)Covariates
summary(m)
Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ predicted.Z * inDegree + propCorr + desirability +
(predicted.Z + inDegree | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
6656.2 6741.9 -3315.1 6630.2 5375
Scaled residuals:
Min 1Q Median 3Q Max
-4.5514 -0.8888 0.4592 0.7783 4.4090
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.0000000 0.00000
subID (Intercept) 0.0000000 0.00000
predicted.Z 0.5970943 0.77272 NaN
inDegree 0.0002242 0.01497 NaN -0.11
Number of obs: 5388, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -2.130181 0.407992 -5.221 1.78e-07 ***
predicted.Z 0.206506 0.150277 1.374 0.169
inDegree 0.001190 0.003729 0.319 0.750
propCorr 4.490776 0.229122 19.600 < 2e-16 ***
desirability 0.032646 0.068194 0.479 0.632
predicted.Z:inDegree 0.005562 0.003680 1.511 0.131
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) prdc.Z inDegr prpCrr dsrblt
predicted.Z 0.030
inDegree 0.021 -0.069
propCorr -0.251 0.012 0.026
desirabilty -0.929 -0.024 -0.152 -0.036
prdctd.Z:nD 0.010 -0.314 0.023 0.001 -0.008
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')Do people self-anchor more for higher outdegree traits?
No covariates
m <- glmer( ingChoiceN ~ predicted.Z * outDegree + ( predicted.Z + outDegree | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)Covariates
m <- glmer( ingChoiceN ~ predicted.Z * outDegree + propCorr + desirability + ( predicted.Z + outDegree | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)
ggpredict(m, c("predicted.Z", "outDegree")) %>% plot(show.title=F) + xlab("Cross-Validated Self-Descriptiveness") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()Do cross-validated similarity*self-evaluation predictions predict ingroup choices, regardless of whether it was seen prior or not?
No covariates
m <- glmer( ingChoiceN ~ predicted.Z * novel + ( predicted.Z + novel | subID) , data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ predicted.Z * novel + (predicted.Z + novel | subID)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
7072.4 7138.3 -3526.2 7052.4 5378
Scaled residuals:
Min 1Q Median 3Q Max
-2.5663 -1.0129 0.6074 0.8791 2.0525
Random effects:
Groups Name Variance Std.Dev. Corr
subID (Intercept) 3.062e-01 0.553356
predicted.Z 4.235e-04 0.020579 1.00
novelHeld Out 9.471e-05 0.009732 1.00 1.00
Number of obs: 5388, groups: subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.29103 0.09680 3.007 0.00264 **
predicted.Z 0.27323 0.09591 2.849 0.00439 **
novelHeld Out 0.04090 0.06143 0.666 0.50560
predicted.Z:novelHeld Out 0.01432 0.06454 0.222 0.82443
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) prdc.Z nvlHlO
predicted.Z 0.081
novelHeldOt -0.308 0.086
prdctd.Z:HO 0.087 -0.376 -0.053
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')Covariates
m <- glmer( ingChoiceN ~ predicted.Z * novel + propCorr + desirability + ( predicted.Z + novel | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
r2beta(m)
ggpredict(m, c("predicted.Z", "novel")) %>% plot(show.title=F)+ xlab("Cross-Validated Self-Descriptiveness") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa() + scale_color_discrete(labels = c("Trained","Held-Out"))
ggsave("~/Documents/UC Riverside/Studies/Self-Anchoring/Figures/CVpredictionGeneralize.tiff",dpi=600)Does generalization depend on outdegree?
No covariates
m <- glmer( ingChoiceN ~ predicted.Z * novel * outDegree + ( predicted.Z + novel | subID) , data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ predicted.Z * novel * outDegree + (predicted.Z + novel | subID)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
7077.5 7169.8 -3524.7 7049.5 5374
Scaled residuals:
Min 1Q Median 3Q Max
-2.6040 -1.0156 0.6007 0.8775 2.0801
Random effects:
Groups Name Variance Std.Dev. Corr
subID (Intercept) 0.3060322 0.55320
predicted.Z 0.0006169 0.02484 1.00
novelHeld Out 0.0001158 0.01076 1.00 1.00
Number of obs: 5388, groups: subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.225934 0.117025 1.931 0.0535 .
predicted.Z 0.242491 0.116671 2.078 0.0377 *
novelHeld Out 0.073738 0.116367 0.634 0.5263
outDegree 0.003083 0.003131 0.985 0.3248
predicted.Z:novelHeld Out -0.053561 0.116903 -0.458 0.6468
predicted.Z:outDegree 0.001036 0.003233 0.320 0.7487
novelHeld Out:outDegree -0.001656 0.004670 -0.355 0.7230
predicted.Z:novelHeld Out:outDegree 0.003237 0.004635 0.698 0.4849
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) prdc.Z nvlHlO outDgr pr.Z:HO pr.Z:D nvHO:D
predicted.Z 0.072
novelHeldOt -0.444 0.054
outDegree -0.562 -0.006 0.557
prdctd.Z:HO 0.057 -0.500 0.023 -0.045
prdctd.Z:tD 0.052 -0.571 -0.048 -0.108 0.577
nvlHldOt:tD 0.373 -0.028 -0.849 -0.669 -0.031 0.072
prdc.Z:HO:D -0.032 0.401 -0.028 0.074 -0.835 -0.699 0.016
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')Covariates
m <- glmer( ingChoiceN ~ predicted.Z * novel * outDegree + propCorr + desirability + ( predicted.Z + novel | subID) , data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ predicted.Z * novel * outDegree + propCorr + desirability +
(predicted.Z + novel | subID)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
6654.1 6759.6 -3311.0 6622.1 5372
Scaled residuals:
Min 1Q Median 3Q Max
-4.6625 -0.8920 0.4623 0.7856 4.0329
Random effects:
Groups Name Variance Std.Dev. Corr
subID (Intercept) 0.3311901 0.57549
predicted.Z 0.0002513 0.01585 -1.00
novelHeld Out 0.0025627 0.05062 1.00 -1.00
Number of obs: 5388, groups: subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -2.0835900 0.4370594 -4.767 1.87e-06 ***
predicted.Z 0.2817766 0.1218493 2.313 0.0208 *
novelHeld Out 0.1015024 0.1214803 0.836 0.4034
outDegree 0.0035754 0.0034356 1.041 0.2980
propCorr 4.4974214 0.2285401 19.679 < 2e-16 ***
desirability 0.0085942 0.0746937 0.115 0.9084
predicted.Z:novelHeld Out -0.0721766 0.1221076 -0.591 0.5545
predicted.Z:outDegree 0.0003677 0.0033374 0.110 0.9123
novelHeld Out:outDegree -0.0031030 0.0048310 -0.642 0.5207
predicted.Z:novelHeld Out:outDegree 0.0044562 0.0048146 0.926 0.3547
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) prdc.Z nvlHlO outDgr prpCrr dsrblt pr.Z:HO pr.Z:D nvHO:D
predicted.Z 0.018
novelHeldOt -0.132 0.060
outDegree 0.167 0.009 0.516
propCorr -0.230 0.031 0.017 0.021
desirabilty -0.925 -0.028 0.016 -0.342 -0.034
prdctd.Z:HO 0.013 -0.453 0.023 -0.054 -0.009 0.007
prdctd.Z:tD 0.019 -0.572 -0.052 -0.109 -0.012 0.000 0.577
nvlHldOt:tD 0.121 -0.035 -0.848 -0.623 -0.019 -0.013 -0.028 0.077
prdc.Z:HO:D -0.014 0.398 -0.026 0.075 0.015 0.001 -0.836 -0.695 0.013
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")r2beta(m)boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular') Effect Rsq upper.CL lower.CL
1 Model 0.085 0.100 0.072
5 propCorr 0.069 0.083 0.057
2 predicted.Z 0.002 0.005 0.000
4 outDegree 0.000 0.002 0.000
10 predicted.Z:novelHeld Out:outDegree 0.000 0.001 0.000
3 novelHeld Out 0.000 0.001 0.000
9 novelHeld Out:outDegree 0.000 0.001 0.000
7 predicted.Z:novelHeld Out 0.000 0.001 0.000
6 desirability 0.000 0.001 0.000
8 predicted.Z:outDegree 0.000 0.001 0.000ggpredict(m, c("predicted.Z", "outDegree" ,"novel")) %>% plot(show.title=F)+ xlab("Cross-Validated Self-Descriptiveness") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()Data were 'prettified'. Consider using `terms="predicted.Z [all]"` to get smooth plots.ggsave("~/Documents/UC Riverside/Studies/Self-Anchoring/Figures/CVpredictionGeneralize.tiff",dpi=600)Saving 7.29 x 4.51 in image
Does generalization depend on indegree?
No covariates
m <- glmer( ingChoiceN ~ predicted.Z * novel * inDegree + ( predicted.Z + novel | subID) , data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ predicted.Z * novel * inDegree + (predicted.Z + novel | subID)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
7077.4 7169.7 -3524.7 7049.4 5374
Scaled residuals:
Min 1Q Median 3Q Max
-2.5758 -1.0135 0.5989 0.8737 2.2289
Random effects:
Groups Name Variance Std.Dev. Corr
subID (Intercept) 3.095e-01 0.556356
predicted.Z 5.908e-04 0.024306 1.00
novelHeld Out 5.933e-05 0.007703 1.00 1.00
Number of obs: 5388, groups: subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.3288522 0.1251085 2.629 0.00858 **
predicted.Z 0.1776097 0.1256027 1.414 0.15734
novelHeld Out -0.0070703 0.1297527 -0.054 0.95654
inDegree -0.0018145 0.0037459 -0.484 0.62811
predicted.Z:novelHeld Out 0.0234077 0.1300056 0.180 0.85711
predicted.Z:inDegree 0.0046982 0.0038152 1.231 0.21816
novelHeld Out:inDegree 0.0022760 0.0053761 0.423 0.67203
predicted.Z:novelHeld Out:inDegree -0.0004284 0.0053609 -0.080 0.93631
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) prdc.Z nvlHlO inDegr pr.Z:HO pr.Z:D nvHO:D
predicted.Z 0.067
novelHeldOt -0.488 0.046
inDegree -0.628 -0.013 0.599
prdctd.Z:HO 0.048 -0.543 0.027 -0.032
prdctd.Z:nD 0.042 -0.637 -0.038 -0.075 0.621
nvlHldOt:nD 0.433 -0.022 -0.880 -0.695 -0.032 0.053
prdc.Z:HO:D -0.027 0.455 -0.030 0.054 -0.867 -0.713 0.020
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')Covariates
summary(m)
Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ predicted.Z * novel * inDegree + (predicted.Z + novel | subID)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
4842.6 4929.6 -2407.3 4814.6 3676
Scaled residuals:
Min 1Q Median 3Q Max
-2.3708 -1.0425 0.6081 0.8478 2.1489
Random effects:
Groups Name Variance Std.Dev. Corr
subID (Intercept) 0.297726 0.54564
predicted.Z 0.014331 0.11971 -0.94
novelHeld Out 0.004817 0.06941 0.06 0.29
Number of obs: 3690, groups: subID, 29
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.3072752 0.1489679 2.063 0.0391 *
predicted.Z 0.2147101 0.1427624 1.504 0.1326
novelHeld Out -0.0106251 0.1574787 -0.067 0.9462
inDegree 0.0001678 0.0045112 0.037 0.9703
predicted.Z:novelHeld Out -0.1367979 0.1585589 -0.863 0.3883
predicted.Z:inDegree 0.0019902 0.0043923 0.453 0.6505
novelHeld Out:inDegree 0.0005728 0.0065070 0.088 0.9298
predicted.Z:novelHeld Out:inDegree 0.0040134 0.0066092 0.607 0.5437
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) prdc.Z nvlHlO inDegr pr.Z:HO pr.Z:D nvHO:D
predicted.Z -0.172
novelHeldOt -0.495 0.045
inDegree -0.626 -0.007 0.598
prdctd.Z:HO 0.043 -0.485 0.019 -0.033
prdctd.Z:nD 0.041 -0.652 -0.035 -0.069 0.585
nvlHldOt:nD 0.437 -0.020 -0.878 -0.693 -0.027 0.048
prdc.Z:HO:D -0.024 0.429 -0.025 0.046 -0.873 -0.666 0.020Neighboring Dependencies Predicting Choices
No covariates
m <- glmer( ingChoiceN ~ neighAveOutSE.Z + ( neighAveOutSE.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ neighAveOutSE.Z + (neighAveOutSE.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
8135.8 8176.2 -4061.9 8123.8 6221
Scaled residuals:
Min 1Q Median 3Q Max
-2.8785 -1.0011 0.5203 0.8853 2.4945
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.0000 0.0000
subID (Intercept) 0.4271 0.6535
neighAveOutSE.Z 0.2070 0.4550 0.24
Number of obs: 6227, groups: trait, 147; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.29168 0.10780 2.706 0.00682 **
neighAveOutSE.Z 0.17689 0.08467 2.089 0.03669 *
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr)
nghAvOtSE.Z 0.174
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')Covariates
summary(m)
Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ neighAveOutSE.Z + propCorr + desirability + (neighAveOutSE.Z |
subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
7624.0 7677.9 -3804.0 7608.0 6219
Scaled residuals:
Min 1Q Median 3Q Max
-4.7522 -0.8558 0.4295 0.7816 4.1533
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.0000 0.0000
subID (Intercept) 0.4503 0.6710
neighAveOutSE.Z 0.1639 0.4048 0.31
Number of obs: 6227, groups: trait, 147; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -1.93132 0.39235 -4.922 8.55e-07 ***
neighAveOutSE.Z 0.23308 0.07962 2.927 0.00342 **
propCorr 4.74189 0.21941 21.612 < 2e-16 ***
desirability -0.02581 0.06293 -0.410 0.68177
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) nAOSE. prpCrr
nghAvOtSE.Z 0.112
propCorr -0.241 0.038
desirabilty -0.919 -0.065 -0.039
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')Generalization of Outdegree Neighboring Self-Evaluations
No covariates
m <- glmer( ingChoiceN ~ neighAveOutSE.Z * novel + ( neighAveOutSE.Z + novel | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)Covariates
m <- glmer( ingChoiceN ~ neighAveOutSE.Z * novel + propCorr + desirability + ( neighAveOutSE.Z + novel | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ neighAveOutSE.Z * novel + propCorr + desirability +
(neighAveOutSE.Z + novel | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
7632.1 7719.7 -3803.0 7606.1 6214
Scaled residuals:
Min 1Q Median 3Q Max
-4.9210 -0.8534 0.4273 0.7822 4.1241
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.000000 0.00000
subID (Intercept) 0.436805 0.66091
neighAveOutSE.Z 0.161881 0.40234 0.28
novelHeld Out 0.001903 0.04362 0.38 0.99
Number of obs: 6227, groups: trait, 147; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -1.94646 0.39272 -4.956 7.18e-07 ***
neighAveOutSE.Z 0.20730 0.08225 2.520 0.0117 *
novelHeld Out 0.02661 0.05781 0.460 0.6453
propCorr 4.74567 0.21958 21.613 < 2e-16 ***
desirability -0.02516 0.06293 -0.400 0.6893
neighAveOutSE.Z:novelHeld Out 0.06926 0.05848 1.184 0.2363
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) nAOSE. nvlHlO prpCrr dsrblt
nghAvOtSE.Z 0.105
novelHeldOt -0.051 0.071
propCorr -0.241 0.032 0.003
desirabilty -0.918 -0.065 0.003 -0.039
ngAOSE.Z:HO -0.011 -0.263 0.024 0.020 0.008
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")r2beta(m)boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular') Effect Rsq upper.CL lower.CL
1 Model 0.080 0.094 0.068
4 propCorr 0.072 0.085 0.061
2 neighAveOutSE.Z 0.004 0.008 0.002
6 neighAveOutSE.Z:novelHeld Out 0.000 0.002 0.000
3 novelHeld Out 0.000 0.001 0.000
5 desirability 0.000 0.001 0.000ggpredict(m, c("neighAveOutSE.Z","novel")) %>% plot(show.title=F)+ xlab("Outwards Neighboring Self-Evaluations") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()Data were 'prettified'. Consider using `terms="neighAveOutSE.Z [all]"` to get smooth plots.ggsave("~/Documents/UC Riverside/Studies/Self-Anchoring/Figures/outdegreeNeighborsGeneralization.tiff",dpi=600)Saving 7.29 x 4.51 in image
Does entropy (i.e., uncertainty) predict likelihood of ingroup choices?
No covariates
m <- glmer( ingChoiceN ~ entropy.Z + ( entropy.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ entropy.Z + (entropy.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
8206.5 8246.9 -4097.2 8194.5 6271
Scaled residuals:
Min 1Q Median 3Q Max
-3.8857 -0.9898 0.4813 0.8925 2.6246
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.000 0.000
subID (Intercept) 2.491 1.578
entropy.Z 2.527 1.590 -0.50
Number of obs: 6277, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.4721 0.2672 1.767 0.0772 .
entropy.Z -0.4455 0.2776 -1.605 0.1085
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr)
entropy.Z -0.404
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')Covariates
m <- glmer( ingChoiceN ~ entropy.Z + propCorr + desirability + ( entropy.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ entropy.Z + propCorr + desirability + (entropy.Z |
subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
7668.0 7721.9 -3826.0 7652.0 6269
Scaled residuals:
Min 1Q Median 3Q Max
-5.8533 -0.8442 0.4042 0.7714 5.0292
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.000 0.000
subID (Intercept) 3.376 1.837
entropy.Z 3.216 1.793 -0.64
Number of obs: 6277, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -1.80823 0.49355 -3.664 0.000249 ***
entropy.Z -0.39190 0.30816 -1.272 0.203465
propCorr 4.91308 0.22429 21.905 < 2e-16 ***
desirability -0.03031 0.06432 -0.471 0.637446
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) entr.Z prpCrr
entropy.Z -0.351
propCorr -0.195 0.004
desirabilty -0.751 0.021 -0.042
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")r2beta(m)boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular')
boundary (singular) fit: see help('isSingular') Effect Rsq upper.CL lower.CL
1 Model 0.072 0.084 0.060
3 propCorr 0.055 0.066 0.044
2 entropy.Z 0.018 0.025 0.012
4 desirability 0.000 0.001 0.000ggpredict(m, c("entropy.Z")) %>% plot(show.title=F) + xlab("Uncertainty") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()Data were 'prettified'. Consider using `terms="entropy.Z [all]"` to get smooth plots.ggsave("~/Documents/UC Riverside/Studies/Self-Anchoring/Figures/Uncertainty.tiff",dpi=600)Saving 7.29 x 4.51 in image
Does a linear trend of similarity-based probabilities predict ingroup choices?
No covariates
m <- glmer( ingChoiceN ~ slope.Z + ( slope.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ slope.Z + (slope.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
8108.2 8148.6 -4048.1 8096.2 6271
Scaled residuals:
Min 1Q Median 3Q Max
-7.5074 -0.9707 0.4360 0.8749 3.6255
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.000 0.000
subID (Intercept) 5.717 2.391
slope.Z 7.279 2.698 0.19
Number of obs: 6277, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.1771 0.4026 0.44 0.66008
slope.Z 1.2160 0.4571 2.66 0.00781 **
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr)
slope.Z 0.166
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')Covariates
m <- glmer( ingChoiceN ~ slope.Z + propCorr + desirability + ( slope.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ slope.Z + propCorr + desirability + (slope.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
7621.2 7675.2 -3802.6 7605.2 6269
Scaled residuals:
Min 1Q Median 3Q Max
-8.1650 -0.8309 0.3847 0.7669 3.6155
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 3.197e-19 5.654e-10
subID (Intercept) 3.256e+00 1.805e+00
slope.Z 4.631e+00 2.152e+00 0.18
Number of obs: 6277, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -1.87029 0.49677 -3.765 0.000167 ***
slope.Z 1.22116 0.38451 3.176 0.001494 **
propCorr 4.74542 0.22383 21.201 < 2e-16 ***
desirability -0.06466 0.06497 -0.995 0.319579
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) slop.Z prpCrr
slope.Z 0.147
propCorr -0.191 0.026
desirabilty -0.735 -0.077 -0.051
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")ggpredict(m, c("slope.Z")) %>% plot(show.title=F) + xlab("Linear Trend of Greater Self-Descriptiveness") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()Data were 'prettified'. Consider using `terms="slope.Z [all]"` to get smooth plots.ggsave("~/Documents/UC Riverside/Studies/Self-Anchoring/Figures/Slope.tiff",dpi=600)Saving 7.29 x 4.51 in image
Does a linear trend of similarity-based probabilities predict ingroup choices, controlling for self-descriptiveness?
m <- glmer( ingChoiceN ~ scale(slope) + selfResp.Z + ( scale(slope) + selfResp.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ scale(slope) + selfResp.Z + (scale(slope) + selfResp.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
3324.8 3383.3 -1652.4 3304.8 2546
Scaled residuals:
Min 1Q Median 3Q Max
-3.0960 -1.0011 0.5507 0.8387 2.3694
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.00000 0.0000
subID (Intercept) 0.38198 0.6180
scale(slope) 0.04406 0.2099 -0.99
selfResp.Z 0.13234 0.3638 0.55 -0.66
Number of obs: 2556, groups: trait, 148; subID, 29
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.27038 0.12721 2.126 0.0335 *
scale(slope) 0.21730 0.11988 1.813 0.0699 .
selfResp.Z 0.19319 0.08783 2.200 0.0278 *
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) scl(s)
scale(slop) -0.406
selfResp.Z 0.403 -0.454
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")Does a non-parametric trend of similarity-based probabilities predict ingroup choices, controlling for self-descriptiveness?
m <- glmer( ingChoiceN ~ scale(nlslope) + selfResp.Z + ( scale(nlslope) + selfResp.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ scale(nlslope) + selfResp.Z + (scale(nlslope) + selfResp.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
3327.3 3385.7 -1653.6 3307.3 2546
Scaled residuals:
Min 1Q Median 3Q Max
-3.0256 -0.9895 0.5363 0.8481 2.3016
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.0000 0.0000
subID (Intercept) 0.4056 0.6369
scale(nlslope) 0.2145 0.4632 -0.24
selfResp.Z 0.1390 0.3728 0.62 -0.44
Number of obs: 2556, groups: trait, 148; subID, 29
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.35811 0.14766 2.425 0.0153 *
scale(nlslope) 0.17096 0.14329 1.193 0.2328
selfResp.Z 0.20564 0.08781 2.342 0.0192 *
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) scl(n)
scal(nlslp) -0.073
selfResp.Z 0.393 -0.389
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")Does a linear trend of similarity-based probabilities predict ingroup choices?
m <- glmer( ingChoiceN ~ slope.Z + predicted.Z + ( slope.Z + predicted.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ slope.Z + predicted.Z + (slope.Z + predicted.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
6817.3 6883.2 -3398.6 6797.3 5378
Scaled residuals:
Min 1Q Median 3Q Max
-9.6167 -0.9885 0.4410 0.8385 2.5346
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 7.538e-15 8.682e-08
subID (Intercept) 5.908e-01 7.686e-01
slope.Z 1.744e+01 4.176e+00 -0.63
predicted.Z 1.611e+01 4.013e+00 0.63 -1.00
Number of obs: 5388, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.1207 0.1269 0.951 0.3416
slope.Z 1.6286 0.7111 2.290 0.0220 *
predicted.Z -1.3225 0.6924 -1.910 0.0561 .
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) slop.Z
slope.Z -0.632
predicted.Z 0.638 -0.991
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")Backwards solution: Can you predict self-evaluations from similarity to ingroup and outgroup choices?
m <- lmer( scale(selfResp) ~ scale(inGsim) + scale(outGsim) + ( scale(inGsim) + scale(outGsim) | subID) + (1 | trait), data = fullTrain)Model failed to converge with max|grad| = 0.00239224 (tol = 0.002, component 1)summary(m)Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
Formula: scale(selfResp) ~ scale(inGsim) + scale(outGsim) + (scale(inGsim) +
scale(outGsim) | subID) + (1 | trait)
Data: fullTrain
REML criterion at convergence: 9640.5
Scaled residuals:
Min 1Q Median 3Q Max
-4.1528 -0.6037 0.0680 0.6497 2.9224
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.09989 0.3160
subID (Intercept) 0.20570 0.4535
scale(inGsim) 0.02907 0.1705 -0.26
scale(outGsim) 0.02580 0.1606 0.22 -0.97
Residual 0.65418 0.8088
Number of obs: 3811, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error df t value Pr(>|t|)
(Intercept) -0.01146 0.07520 53.75711 -0.152 0.879491
scale(inGsim) 0.15216 0.03659 54.07607 4.158 0.000115 ***
scale(outGsim) -0.02811 0.03435 41.30898 -0.818 0.417848
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) scl(nG)
scale(nGsm) -0.175
scale(tGsm) 0.143 -0.558
optimizer (nloptwrap) convergence code: 0 (OK)
Model failed to converge with max|grad| = 0.00239224 (tol = 0.002, component 1)tidy(m,conf.int=TRUE,effects="fixed")ggpredict(m, c("inGsim")) %>% plot(show.title=F) + xlab("Similarity to Ingroup Choices") + ylab("Self-Evaluation") + jtools::theme_apa()
m <- glmer( ingChoiceN ~ scale(slope) * novel + ( scale(slope) + novel | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ scale(slope) * novel + (scale(slope) + novel | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
8116.8 8191.0 -4047.4 8094.8 6266
Scaled residuals:
Min 1Q Median 3Q Max
-7.6460 -0.9719 0.4342 0.8748 3.6722
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 2.106e-15 4.589e-08
subID (Intercept) 5.839e+00 2.417e+00
scale(slope) 7.265e+00 2.695e+00 0.18
novelHeld Out 4.776e-03 6.911e-02 -0.74 0.53
Number of obs: 6277, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.181581 0.406997 0.446 0.65549
scale(slope) 1.211092 0.457627 2.646 0.00813 **
novelHeld Out 0.020056 0.056590 0.354 0.72304
scale(slope):novelHeld Out 0.001002 0.063191 0.016 0.98735
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) scl(s) nvlHlO
scale(slop) 0.157
novelHeldOt -0.179 0.082
scl(slp):HO 0.004 -0.058 0.030
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")summary(m)
Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ eSE + (eSE | subID)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
4785.1 4816.1 -2387.5 4775.1 3635
Scaled residuals:
Min 1Q Median 3Q Max
-2.6814 -1.0139 0.5896 0.8615 2.8232
Random effects:
Groups Name Variance Std.Dev. Corr
subID (Intercept) 24.66 4.965
eSE 16.76 4.094 -1.00
Number of obs: 3640, groups: subID, 25
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -0.4974 1.1746 -0.424 0.672
eSE 0.6004 0.9522 0.631 0.528
Correlation of Fixed Effects:
(Intr)
eSE -0.996summary(m)
Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: ingChoiceN ~ sSE * novel + (sSE | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
4791.8 4841.4 -2387.9 4775.8 3632
Scaled residuals:
Min 1Q Median 3Q Max
-2.6486 -1.0125 0.5929 0.8627 2.7918
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.000 0.000
subID (Intercept) 1.134 1.065
sSE 26.117 5.111 -0.90
Number of obs: 3640, groups: trait, 148; subID, 25
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.03974 0.29415 0.135 0.893
sSE 0.89300 1.28620 0.694 0.487
novel1 0.12039 0.32510 0.370 0.711
sSE:novel1 -0.36572 1.26144 -0.290 0.772
Correlation of Fixed Effects:
(Intr) sSE novel1
sSE -0.928
novel1 -0.427 0.366
sSE:novel1 0.413 -0.372 -0.976
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')m <- glmer( ingChoiceN ~ SE.Z * novel + ( SE.Z + novel | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
r2beta(m)summary(m)
Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ scale(oSE) + (scale(oSE) | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
5482.7 5520.8 -2735.3 5470.7 4215
Scaled residuals:
Min 1Q Median 3Q Max
-2.6879 -0.9939 0.5179 0.8500 2.8947
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.0000 0.0000
subID (Intercept) 0.3871 0.6222
scale(oSE) 0.1068 0.3267 0.59
Number of obs: 4221, groups: trait, 148; subID, 29
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.30322 0.12022 2.522 0.0117 *
scale(oSE) 0.08435 0.06924 1.218 0.2232
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr)
scale(oSE) 0.504
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')m <- glmer( as.factor(ingChoiceN) ~ predicted.Z*scale(NTB) + ( predicted.Z | subID) + ( predicted.Z | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
boundary (singular) fit: see help('isSingular')m <- glmer( as.factor(ingChoiceN) ~ predicted.Z*scale(NTB) + ( predicted.Z | subID) + ( predicted.Z | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ predicted.Z * scale(NTB) + (predicted.Z |
subID) + (predicted.Z | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
7069.5 7135.5 -3524.8 7049.5 5378
Scaled residuals:
Min 1Q Median 3Q Max
-2.5031 -1.0174 0.6124 0.8754 2.0570
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 4.970e-14 2.229e-07
predicted.Z 2.168e-14 1.472e-07 1.00
subID (Intercept) 2.908e-01 5.393e-01
predicted.Z 5.770e-04 2.402e-02 1.00
Number of obs: 5388, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.32033 0.09038 3.544 0.000394 ***
predicted.Z 0.29293 0.09455 3.098 0.001947 **
scale(NTB) 0.17693 0.09817 1.802 0.071494 .
predicted.Z:scale(NTB) 0.03974 0.08321 0.478 0.632997
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) prdc.Z s(NTB)
predicted.Z 0.129
scale(NTB) 0.096 0.062
prd.Z:(NTB) 0.136 -0.352 0.421
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(RSE) + ( entropy.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ entropy.Z * scale(RSE) + (entropy.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
4793.6 4843.2 -2388.8 4777.6 3632
Scaled residuals:
Min 1Q Median 3Q Max
-2.8434 -1.0083 0.5747 0.8744 2.3956
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 1.004e-18 1.002e-09
subID (Intercept) 9.301e-01 9.644e-01
entropy.Z 1.594e+00 1.262e+00 -0.55
Number of obs: 3640, groups: trait, 148; subID, 25
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.7127 0.2436 2.925 0.00344 **
entropy.Z -0.5494 0.3071 -1.789 0.07362 .
scale(RSE) -0.2484 0.2335 -1.064 0.28751
entropy.Z:scale(RSE) 0.3395 0.3118 1.089 0.27626
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) entr.Z s(RSE)
entropy.Z -0.412
scale(RSE) -0.019 0.206
ent.Z:(RSE) 0.218 -0.047 -0.388
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("entropy.Z", "RSE")) %>% plot()Data were 'prettified'. Consider using `terms="entropy.Z [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(SCC) + ( entropy.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ entropy.Z * scale(SCC) + (entropy.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
4795.1 4844.7 -2389.6 4779.1 3632
Scaled residuals:
Min 1Q Median 3Q Max
-2.8462 -1.0069 0.5800 0.8735 2.3915
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 6.577e-20 2.564e-10
subID (Intercept) 9.521e-01 9.757e-01
entropy.Z 1.680e+00 1.296e+00 -0.56
Number of obs: 3640, groups: trait, 148; subID, 25
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.690663 0.243870 2.832 0.00462 **
entropy.Z -0.527405 0.314479 -1.677 0.09353 .
scale(SCC) -0.097378 0.240594 -0.405 0.68567
entropy.Z:scale(SCC) 0.005057 0.299650 0.017 0.98653
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) entr.Z s(SCC)
entropy.Z -0.436
scale(SCC) -0.071 0.122
ent.Z:(SCC) 0.118 0.025 -0.481
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("entropy.Z", "SCC")) %>% plot()Data were 'prettified'. Consider using `terms="entropy.Z [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(DS) + ( entropy.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ entropy.Z * scale(DS) + (entropy.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
4793.8 4843.4 -2388.9 4777.8 3632
Scaled residuals:
Min 1Q Median 3Q Max
-2.8406 -1.0079 0.5813 0.8733 2.4261
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.0000 0.000
subID (Intercept) 0.8798 0.938
entropy.Z 1.6204 1.273 -0.55
Number of obs: 3640, groups: trait, 148; subID, 25
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.7324 0.2379 3.078 0.00208 **
entropy.Z -0.5417 0.3101 -1.747 0.08070 .
scale(DS) 0.2496 0.2290 1.090 0.27583
entropy.Z:scale(DS) -0.3141 0.3095 -1.015 0.31015
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) entr.Z sc(DS)
entropy.Z -0.431
scale(DS) 0.144 -0.206
entr.Z:(DS) -0.214 0.020 -0.448
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("entropy.Z", "DS")) %>% plot()Data were 'prettified'. Consider using `terms="entropy.Z [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(NFC) + ( entropy.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ entropy.Z * scale(NFC) + (entropy.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
4791.1 4840.7 -2387.6 4775.1 3632
Scaled residuals:
Min 1Q Median 3Q Max
-2.8458 -1.0084 0.5964 0.8739 2.4604
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.0000 0.0000
subID (Intercept) 0.7927 0.8903
entropy.Z 1.2373 1.1124 -0.55
Number of obs: 3640, groups: trait, 148; subID, 25
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.7115 0.2278 3.123 0.00179 **
entropy.Z -0.5087 0.2797 -1.819 0.06897 .
scale(NFC) 0.2597 0.2271 1.144 0.25278
entropy.Z:scale(NFC) -0.5659 0.2716 -2.083 0.03722 *
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) entr.Z s(NFC)
entropy.Z -0.442
scale(NFC) 0.112 -0.175
ent.Z:(NFC) -0.190 0.048 -0.483
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("entropy.Z", "NFC")) %>% plot()Data were 'prettified'. Consider using `terms="entropy.Z [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(SING.Ind) + ( entropy.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ entropy.Z * scale(SING.Ind) + (entropy.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
4791.7 4841.3 -2387.9 4775.7 3632
Scaled residuals:
Min 1Q Median 3Q Max
-2.8319 -1.0092 0.5749 0.8759 2.4004
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.0000 0.0000
subID (Intercept) 0.6746 0.8214
entropy.Z 1.4260 1.1941 -0.65
Number of obs: 3640, groups: trait, 148; subID, 25
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.6476 0.2177 2.974 0.00294 **
entropy.Z -0.6070 0.2932 -2.071 0.03840 *
scale(SING.Ind) -0.5182 0.2563 -2.022 0.04318 *
entropy.Z:scale(SING.Ind) 0.1566 0.2875 0.545 0.58605
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) entr.Z s(SING
entropy.Z -0.467
scl(SING.I) -0.005 0.244
e.Z:(SING.I 0.228 -0.066 -0.327
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("entropy.Z", "SING.Ind")) %>% plot()Data were 'prettified'. Consider using `terms="entropy.Z [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(SING.Inter) + ( entropy.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ entropy.Z * scale(SING.Inter) + (entropy.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
4791.4 4841.0 -2387.7 4775.4 3632
Scaled residuals:
Min 1Q Median 3Q Max
-2.8785 -1.0138 0.5936 0.8820 2.4011
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.0000 0.0000
subID (Intercept) 0.6094 0.7806
entropy.Z 1.7311 1.3157 -0.51
Number of obs: 3640, groups: trait, 148; subID, 25
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.7522 0.2142 3.512 0.000444 ***
entropy.Z -0.4557 0.3140 -1.451 0.146682
scale(SING.Inter) 0.5286 0.2593 2.038 0.041513 *
entropy.Z:scale(SING.Inter) -0.1277 0.2946 -0.433 0.664789
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) entr.Z s(SING
entropy.Z -0.382
scl(SING.I) 0.237 -0.005
e.Z:(SING.I -0.056 0.040 -0.301
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("entropy.Z", "SING.Inter")) %>% plot()Data were 'prettified'. Consider using `terms="entropy.Z [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(Proto) + ( entropy.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ entropy.Z * scale(Proto) + (entropy.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
4795.2 4844.8 -2389.6 4779.2 3632
Scaled residuals:
Min 1Q Median 3Q Max
-2.8447 -1.0052 0.5806 0.8732 2.3944
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.0000 0.0000
subID (Intercept) 0.9035 0.9505
entropy.Z 1.6478 1.2837 -0.54
Number of obs: 3640, groups: trait, 148; subID, 25
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.69010 0.23886 2.889 0.00386 **
entropy.Z -0.50042 0.31002 -1.614 0.10650
scale(Proto) 0.08185 0.23908 0.342 0.73209
entropy.Z:scale(Proto) -0.09448 0.29866 -0.316 0.75173
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) entr.Z scl(P)
entropy.Z -0.432
scale(Prot) 0.057 0.041
entrp.Z:(P) 0.011 -0.017 -0.281
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("entropy.Z", "Proto")) %>% plot()Data were 'prettified'. Consider using `terms="entropy.Z [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(SI) + ( entropy.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ entropy.Z * scale(SI) + (entropy.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
4790.2 4839.8 -2387.1 4774.2 3632
Scaled residuals:
Min 1Q Median 3Q Max
-2.8302 -1.0044 0.5814 0.8769 2.4447
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.0000 0.0000
subID (Intercept) 0.6831 0.8265
entropy.Z 1.8112 1.3458 -0.64
Number of obs: 3640, groups: trait, 148; subID, 25
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.74323 0.21772 3.414 0.000641 ***
entropy.Z -0.47302 0.31535 -1.500 0.133618
scale(SI) 0.45524 0.21902 2.079 0.037661 *
entropy.Z:scale(SI) -0.01954 0.30810 -0.063 0.949443
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) entr.Z sc(SI)
entropy.Z -0.487
scale(SI) 0.165 -0.075
entr.Z:(SI) -0.024 0.071 -0.503
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("entropy.Z", "SI")) %>% plot()Data were 'prettified'. Consider using `terms="entropy.Z [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(NTB) + ( entropy.Z | subID) + ( entropy.Z | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ entropy.Z * scale(NTB) + (entropy.Z | subID) + (entropy.Z | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
4798.1 4860.1 -2389.0 4778.1 3630
Scaled residuals:
Min 1Q Median 3Q Max
-2.8355 -1.0062 0.5801 0.8745 2.3634
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.000e+00 0.000e+00
entropy.Z 5.571e-16 2.360e-08 NaN
subID (Intercept) 8.986e-01 9.479e-01
entropy.Z 1.595e+00 1.263e+00 -0.57
Number of obs: 3640, groups: trait, 148; subID, 25
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.68431 0.23774 2.878 0.0040 **
entropy.Z -0.52197 0.30393 -1.717 0.0859 .
scale(NTB) 0.24331 0.23185 1.049 0.2940
entropy.Z:scale(NTB) -0.06185 0.29468 -0.210 0.8337
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) entr.Z s(NTB)
entropy.Z -0.452
scale(NTB) 0.040 -0.082
ent.Z:(NTB) -0.066 0.031 -0.534
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("entropy.Z", "NTB")) %>% plot()Data were 'prettified'. Consider using `terms="entropy.Z [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ slope.Z*scale(RSE) + ( slope.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
boundary (singular) fit: see help('isSingular')m <- glmer( as.factor(ingChoiceN) ~ slope.Z*scale(RSE) + ( slope.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ slope.Z * scale(RSE) + (slope.Z | subID) + (1 | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
8108.2 8162.2 -4046.1 8092.2 6269
Scaled residuals:
Min 1Q Median 3Q Max
-7.5446 -0.9753 0.4334 0.8775 3.6256
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 1.047e-14 1.023e-07
subID (Intercept) 5.372e+00 2.318e+00
slope.Z 7.133e+00 2.671e+00 0.18
Number of obs: 6277, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.2029 0.3932 0.516 0.60584
slope.Z 1.2754 0.4536 2.812 0.00492 **
scale(RSE) -0.7906 0.4133 -1.913 0.05575 .
slope.Z:scale(RSE) -0.3153 0.4452 -0.708 0.47887
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) slop.Z s(RSE)
slope.Z 0.156
scale(RSE) -0.030 -0.098
slp.Z:(RSE) -0.090 0.015 0.139
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(RSE) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ scale(desirability) * scale(RSE) + (scale(desirability) |
subID) + (scale(desirability) | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
2111.4 2165.2 -1045.7 2091.4 1594
Scaled residuals:
Min 1Q Median 3Q Max
-3.8959 -1.0144 0.4983 0.9101 1.4069
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.003365 0.05801
scale(desirability) 0.013385 0.11570 1.00
subID (Intercept) 0.415188 0.64435
scale(desirability) 0.001739 0.04170 1.00
Number of obs: 1604, groups: trait, 148; subID, 11
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.38520 0.20272 1.900 0.05741 .
scale(desirability) 0.20932 0.06083 3.441 0.00058 ***
scale(RSE) 0.27336 0.20314 1.346 0.17840
scale(desirability):scale(RSE) 0.02205 0.05729 0.385 0.70036
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) scl(d) s(RSE)
scl(dsrblt) 0.218
scale(RSE) 0.019 0.019
scl():(RSE) 0.018 0.128 0.233
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("desirability", "RSE")) %>% plot()Data were 'prettified'. Consider using `terms="desirability [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(SCC) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ scale(desirability) * scale(SCC) + (scale(desirability) |
subID) + (scale(desirability) | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
2110.0 2163.8 -1045.0 2090.0 1594
Scaled residuals:
Min 1Q Median 3Q Max
-3.8913 -1.0078 0.4896 0.9083 1.3630
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.003354 0.05791
scale(desirability) 0.013479 0.11610 1.00
subID (Intercept) 0.377675 0.61455
scale(desirability) 0.003107 0.05574 1.00
Number of obs: 1604, groups: trait, 148; subID, 11
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.385673 0.194130 1.987 0.046958 *
scale(desirability) 0.209174 0.061907 3.379 0.000728 ***
scale(SCC) 0.337654 0.195663 1.726 0.084403 .
scale(desirability):scale(SCC) -0.006718 0.060638 -0.111 0.911783
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) scl(d) s(SCC)
scl(dsrblt) 0.280
scale(SCC) 0.026 0.024
scl():(SCC) 0.022 0.143 0.293
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("desirability", "SCC")) %>% plot()Data were 'prettified'. Consider using `terms="desirability [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(DS) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ scale(desirability) * scale(DS) + (scale(desirability) |
subID) + (scale(desirability) | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
2110.9 2164.7 -1045.4 2090.9 1594
Scaled residuals:
Min 1Q Median 3Q Max
-3.7639 -1.0088 0.4900 0.9098 1.4151
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.0034089 0.05839
scale(desirability) 0.0134907 0.11615 1.00
subID (Intercept) 0.3893895 0.62401
scale(desirability) 0.0009413 0.03068 1.00
Number of obs: 1604, groups: trait, 148; subID, 11
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.38260 0.19680 1.944 0.051891 .
scale(desirability) 0.20787 0.06023 3.451 0.000558 ***
scale(DS) -0.29740 0.19610 -1.517 0.129382
scale(desirability):scale(DS) -0.03279 0.05445 -0.602 0.547033
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) scl(d) sc(DS)
scl(dsrblt) 0.167
scale(DS) -0.015 -0.017
scl(d):(DS) -0.015 -0.103 0.179
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("desirability", "DS")) %>% plot()Data were 'prettified'. Consider using `terms="desirability [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(NFC) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ scale(desirability) * scale(NFC) + (scale(desirability) |
subID) + (scale(desirability) | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
2112.6 2166.4 -1046.3 2092.6 1594
Scaled residuals:
Min 1Q Median 3Q Max
-3.8577 -1.0118 0.4889 0.9094 1.3512
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.003355 0.05792
scale(desirability) 0.013450 0.11598 1.00
subID (Intercept) 0.479426 0.69241
scale(desirability) 0.002268 0.04762 1.00
Number of obs: 1604, groups: trait, 148; subID, 11
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.38517 0.21664 1.778 0.075415 .
scale(desirability) 0.20871 0.06126 3.407 0.000657 ***
scale(NFC) -0.09903 0.21536 -0.460 0.645636
scale(desirability):scale(NFC) 0.01942 0.05410 0.359 0.719619
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) scl(d) s(NFC)
scl(dsrblt) 0.244
scale(NFC) -0.008 -0.007
scl():(NFC) -0.008 -0.060 0.264
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("desirability", "NFC")) %>% plot()Data were 'prettified'. Consider using `terms="desirability [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(SING.Ind) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ scale(desirability) * scale(SING.Ind) +
(scale(desirability) | subID) + (scale(desirability) | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
2112.7 2166.5 -1046.4 2092.7 1594
Scaled residuals:
Min 1Q Median 3Q Max
-3.8602 -1.0147 0.4910 0.9059 1.3673
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.003337 0.05777
scale(desirability) 0.013431 0.11589 1.00
subID (Intercept) 0.486231 0.69730
scale(desirability) 0.002218 0.04710 1.00
Number of obs: 1604, groups: trait, 148; subID, 11
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.38508 0.21806 1.766 0.077406 .
scale(desirability) 0.20921 0.06118 3.419 0.000628 ***
scale(SING.Ind) 0.05346 0.21663 0.247 0.805083
scale(desirability):scale(SING.Ind) -0.02489 0.05367 -0.464 0.642820
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) scl(d) s(SING
scl(dsrblt) 0.242
scl(SING.I) 0.004 0.003
s():(SING.I 0.003 0.022 0.263
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("desirability", "SING.Ind")) %>% plot()Data were 'prettified'. Consider using `terms="desirability [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(SING.Inter) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ scale(desirability) * scale(SING.Inter) +
(scale(desirability) | subID) + (scale(desirability) | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
2110.4 2164.2 -1045.2 2090.4 1594
Scaled residuals:
Min 1Q Median 3Q Max
-3.8256 -1.0104 0.4934 0.9125 1.4150
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.0000000 0.00000
scale(desirability) 0.0093185 0.09653 NaN
subID (Intercept) 0.3727206 0.61051
scale(desirability) 0.0009385 0.03063 1.00
Number of obs: 1604, groups: trait, 148; subID, 11
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.38345 0.19280 1.989 0.046716 *
scale(desirability) 0.20642 0.05956 3.466 0.000529 ***
scale(SING.Inter) -0.33236 0.19353 -1.717 0.085910 .
scale(desirability):scale(SING.Inter) -0.03516 0.05701 -0.617 0.537466
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) scl(d) s(SING
scl(dsrblt) 0.162
scl(SING.I) -0.022 -0.021
s():(SING.I -0.020 -0.138 0.177
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("desirability", "SING.Inter")) %>% plot()Data were 'prettified'. Consider using `terms="desirability [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(Proto) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ scale(desirability) * scale(Proto) +
(scale(desirability) | subID) + (scale(desirability) | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
2109.2 2163.0 -1044.6 2089.2 1594
Scaled residuals:
Min 1Q Median 3Q Max
-4.3834 -1.0152 0.5623 0.9062 1.4029
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.003279 0.05726
scale(desirability) 0.013172 0.11477 1.00
subID (Intercept) 0.374479 0.61195
scale(desirability) 0.001273 0.03567 1.00
Number of obs: 1604, groups: trait, 148; subID, 11
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.39167 0.19357 2.023 0.043030 *
scale(desirability) 0.21533 0.06089 3.536 0.000406 ***
scale(Proto) -0.38362 0.20188 -1.900 0.057402 .
scale(desirability):scale(Proto) -0.07237 0.07165 -1.010 0.312464
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) scl(d) scl(P)
scl(dsrblt) 0.194
scale(Prot) -0.043 -0.047
scl(ds):(P) -0.038 -0.225 0.229
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("desirability", "Proto")) %>% plot()Data were 'prettified'. Consider using `terms="desirability [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(SI) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ scale(desirability) * scale(SI) + (scale(desirability) |
subID) + (scale(desirability) | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
2110.7 2164.5 -1045.4 2090.7 1594
Scaled residuals:
Min 1Q Median 3Q Max
-4.0641 -1.0169 0.5313 0.9074 1.5565
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.003313 0.05756
scale(desirability) 0.013506 0.11621 1.00
subID (Intercept) 0.492358 0.70168
scale(desirability) 0.002593 0.05092 1.00
Number of obs: 1604, groups: trait, 148; subID, 11
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.38629 0.21938 1.761 0.078272 .
scale(desirability) 0.21359 0.06156 3.470 0.000521 ***
scale(SI) -0.05538 0.21816 -0.254 0.799632
scale(desirability):scale(SI) -0.08211 0.05464 -1.503 0.132865
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) scl(d) sc(SI)
scl(dsrblt) 0.260
scale(SI) -0.008 -0.009
scl(d):(SI) -0.009 -0.079 0.280
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("desirability", "SI")) %>% plot()Data were 'prettified'. Consider using `terms="desirability [all]"` to get smooth plots.
m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(NTB) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)boundary (singular) fit: see help('isSingular')summary(m)Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ scale(desirability) * scale(NTB) + (scale(desirability) |
subID) + (scale(desirability) | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
2112.8 2166.6 -1046.4 2092.8 1594
Scaled residuals:
Min 1Q Median 3Q Max
-3.9039 -1.0131 0.5005 0.9074 1.4211
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 0.00337 0.05805
scale(desirability) 0.01338 0.11569 1.00
subID (Intercept) 0.47789 0.69130
scale(desirability) 0.00211 0.04593 1.00
Number of obs: 1604, groups: trait, 148; subID, 11
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.38539 0.21633 1.782 0.07483 .
scale(desirability) 0.20947 0.06112 3.427 0.00061 ***
scale(NTB) -0.11353 0.21542 -0.527 0.59819
scale(desirability):scale(NTB) -0.01384 0.05480 -0.253 0.80060
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) scl(d) s(NTB)
scl(dsrblt) 0.237
scale(NTB) -0.010 -0.010
scl():(NTB) -0.009 -0.075 0.255
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')ggpredict(m, c("desirability", "NTB")) %>% plot()Data were 'prettified'. Consider using `terms="desirability [all]"` to get smooth plots.
summary(m)
Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
Family: binomial ( logit )
Formula: as.factor(ingChoiceN) ~ predicted.Z * novel * scale(NFC) + (predicted.Z +
novel | subID) + (SE.Z * as.factor(novel) | trait)
Data: fullTest
Control: glmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
AIC BIC logLik deviance df.resid
7096.7 7254.9 -3524.3 7048.7 5364
Scaled residuals:
Min 1Q Median 3Q Max
-2.5776 -1.0099 0.6120 0.8739 2.0613
Random effects:
Groups Name Variance Std.Dev. Corr
trait (Intercept) 2.406e-07 0.0004905
SE.Z 1.919e-04 0.0138525 -0.80
as.factor(novel)Held Out 3.252e-05 0.0057030 -0.82 1.00
SE.Z:as.factor(novel)Held Out 2.260e-02 0.1503186 -0.79 1.00 1.00
subID (Intercept) 3.192e-01 0.5649467
predicted.Z 5.547e-03 0.0744757 0.55
novelHeld Out 9.336e-04 0.0305543 0.17 0.92
Number of obs: 5388, groups: trait, 148; subID, 43
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.30788 0.10120 3.042 0.00235 **
predicted.Z 0.23271 0.11743 1.982 0.04750 *
novelHeld Out 0.03714 0.06458 0.575 0.56526
scale(NFC) -0.03902 0.10602 -0.368 0.71287
predicted.Z:novelHeld Out 0.01637 0.07181 0.228 0.81966
predicted.Z:scale(NFC) -0.10215 0.10282 -0.993 0.32050
novelHeld Out:scale(NFC) 0.04980 0.06121 0.814 0.41593
predicted.Z:novelHeld Out:scale(NFC) 0.03690 0.06466 0.571 0.56821
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Correlation of Fixed Effects:
(Intr) prdc.Z nvlHlO s(NFC) pr.Z:HO p.Z:(N nHO:(N
predicted.Z 0.012
novelHeldOt -0.311 0.130
scale(NFC) -0.060 -0.142 -0.050
prdctd.Z:HO 0.117 -0.378 -0.148 0.081
prd.Z:(NFC) -0.147 0.214 0.025 0.351 -0.010
nvlHO:(NFC) -0.027 0.023 0.028 -0.244 -0.125 0.013
p.Z:HO:(NFC 0.059 -0.052 -0.185 -0.013 0.309 -0.370 0.117
optimizer (bobyqa) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel)*scale(SCC) + ( SE.Z+as.factor(novel) | subID) + ( SE.Z+as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)
ggpredict(m, c("SE","novel","SCC")) %>% plot()m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel)*scale(DS) + ( SE.Z+as.factor(novel) | subID) + ( SE.Z+as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)
ggpredict(m, c("SE","novel","DS")) %>% plot()m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel)*scale(NFC) + ( SE.Z+as.factor(novel) | subID) + ( SE.Z+as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)
ggpredict(m, c("SE","novel", "NFC")) %>% plot()m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel)*scale(SING.Ind) + ( SE.Z+as.factor(novel) | subID) + ( SE.Z+as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)
ggpredict(m, c("SE","novel","SING.Ind")) %>% plot()m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel)*scale(SING.Inter) + ( SE.Z+as.factor(novel) | subID) + ( SE.Z+as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)
ggpredict(m, c("SE","novel","SING.Inter")) %>% plot()m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel)*scale(Proto) + ( SE.Z+as.factor(novel) | subID) + ( SE.Z+as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)
ggpredict(m, c("SE", "Proto")) %>% plot()m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel)*scale(SI) + ( SE.Z+as.factor(novel) | subID) + ( SE.Z+as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)
ggpredict(m, c("SE","novel","SI")) %>% plot()m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel)*scale(NTB) + ( SE.Z+as.factor(novel) | subID) + ( SE.Z+as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
optCtrl = list(maxfun = 100000)),
nAGQ = 1)
summary(m)
ggpredict(m, c("SE", "novel", "NTB")) %>% plot()---
title: "R Notebook"
output: html_notebook
---

```{r}
library(lmerTest)
library(ggeffects)
library(dplyr)
library(report)
library(r2glmm)
library(performance)
library(corrr)
library(broom.mixed)
```

```{r}
fullTest <- read.csv("../Cleaning/output/fullTest.csv")
fullTrain <- read.csv("../Cleaning/output/fullTrain.csv")

traitsFreqs <- read.csv("../Cleaning/output/traitFreqOverUnder.csv")
traitsFreqs <- rename(traitsFreqs, props = optionChoiceN)
fullTest <- merge(fullTest, traitsFreqs[c("trait","props")], by = "trait")
fullTest$propCorr <- ifelse(fullTest$Estimator=="Underestimator", 1-fullTest$props, fullTest$props)

uSubs <- unique(fullTest$subID)

indDiffs <- fullTest[!duplicated(fullTest$subID),]
```

```{r}
fullTest$ingChoiceN <- as.factor(fullTest$ingChoiceN)
fullTest$novel <- as.factor(fullTest$novel)
fullTest$selfResp.Z <- scale(fullTest$selfResp)
fullTest$SE.Z <- scale(fullTest$SE)
fullTest$iSE.Z <- scale(fullTest$iSE)
fullTest$oSE.Z <- scale(fullTest$oSE)
fullTest$predicted.Z <- scale(fullTest$predicted)
fullTest$slope.Z <- scale(fullTest$slope)
fullTest$entropy.Z <- scale(fullTest$entropy)
fullTest$WSR.Z <- scale(fullTest$WSR)
fullTest$neighAveOutSE.Z <- scale(fullTest$neighAveOutSE)
fullTest$neighAveAllSE.Z <- scale(fullTest$neighAveAllSE)
fullTest$neighAveInSE.Z <- scale(fullTest$neighAveInSE)
```


```{r}
fullTest$novel <- as.factor(fullTest$novel)
levels(fullTest$novel) <- list("Trained"  = "0", "Held Out" = "1")
```

```{r}
evalMat <- matrix(nrow=148, ncol=1)
evalMat[,1] <- 1:148
evalMat <- as.data.frame(evalMat)
colnames(evalMat) <- c("Idx")
for(i in uSubs){
  eval <- fullTrain$selfResp[fullTrain$subID==i]
  cur <- cbind(fullTrain$Idx[fullTrain$subID==i], eval)
  colnames(cur) <- c("Idx",paste0("e",i))
  evalMat <- merge(evalMat, cur, by = "Idx", all.x = T)
}
```

```{r}
MDSframe <-
  data.frame(Idx=1:148, 
           MDS=cmdscale(dist(evalMat[2:length(evalMat)]), eig=TRUE, k=3)$points
)
fullTest <-merge(fullTest, MDSframe, by = "Idx")
```

```{r}
library(magrittr)
library(dplyr)
library(ggpubr)

mds <- evalMat %>%
  select(2:length(.)) %>%
  dist() %>%          
  isoMDS(k=2) %>%
  .$points %>%
  as_tibble()
colnames(mds) <- c("Dim.1", "Dim.2")

# Plot MDS
ggscatter(mds, x = "Dim.1", y = "Dim.2", 
          label = allPosCents$trait,
          size = 1,
          repel = TRUE)

mds$Idx <- 1:148

fullTest <-merge(fullTest, mds, by = "Idx")
```


```{r}
evalMat <- matrix(nrow=0, ncol=3)
evalMat[,2] <- 1:148
evalMat <- as.data.frame(evalMat)
colnames(evalMat) <- c("subID","Idx","eval")
for(i in uSubs){
  eval <- fullTrain$selfResp[fullTrain$subID==i]
  present <- which(!is.na(eval))
  Idx=fullTrain$Idx[fullTrain$subID==i]
  Idx=Idx[present]
  eval=eval[present]
  cur <- cbind(subID=i,
               Idx = Idx,
               MDS=cmdscale(dist(eval), eig=TRUE, k=1)$points)
  evalMat <- rbind(evalMat, cur)
}
```

```{r}
  
```


```{r}
# prop.test(traitsFreqs$optionChoiceN, traitsFreqs$N, p=rep(.5,length(traitsFreqs$N)))
# 
# m <- glmer( ingChoiceN ~ trait + ( 1 | subID) , data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
#                                     optCtrl = list(maxfun = 100000)),
#     nAGQ = 1)
# 
# fullTest$trait <- as.factor(fullTest$trait)
# contrasts(fullTest$trait) <- contr.sum(148)
# m <- glm(optionChoiceN ~ trait, family = binomial,
#           data = fullTest
#          )
# summary(m)
```


```{r}
# traitsFreqs$trait <- as.factor(traitsFreqs$trait)
# contrasts(traitsFreqs$trait) <- contr.sum(148)
# m <- glm(optionChoiceN ~ 1, family = binomial,
#           data = traitsFreqs
#          )
# summary(m)
# check_overdispersion(m)
# check_model(m)
# 
# m <- glm(optionChoiceN ~ trait, family = quasibinomial,
#           data = traitsFreqs
#          )
# check_overdispersion(m)
# check_model(m)
# 
# t.test()
# 
# m <- glm(optionChoiceN ~ trait, family = poisson,
#           data = traitsFreqs
#          )
# check_overdispersion(m)
# check_model(m)
```

```{r}
propMatrix <- matrix(nrow=148,ncol=7)
for(i in 1:148){
    traitDf <- subset(fullTest, Idx==i)
    test <- t.test(as.numeric(traitDf$ingChoiceN)-1, mu=.50)
    propMatrix[i, ] <- c(i, test$statistic, test$p.value, test$conf.int, test$estimate, test$parameter)
}
colnames(propMatrix) <- c("Idx", "stat", "p", "LCI", "UCI", "est", "param")
propMatrix <- as.data.frame(propMatrix)
propMatrix$trait <- traitsFreqs$trait
propMatrix <- propMatrix[order(propMatrix$p),]
```

```{r}
x <- indDiffs %>% 
    select(groupHomoph, seHomoph, DS:SING.Inter) %>%
  correlate() %>% 
  focus(groupHomoph) %>%
    arrange(groupHomoph)

x %>% 
  mutate(rowname = factor(rowname, levels = rowname[order(groupHomoph)])) %>%  # Order by correlation strength
  ggplot(aes(x = rowname, y = groupHomoph)) +
    geom_bar(stat = "identity") +
    ylab("Correlation Coefficient") +
    xlab("Individual Differences") + theme_grey(base_size = 9)  + theme(axis.text.x = element_text(angle = 90,hjust = 1)) +
  theme(axis.text.x = element_text( 
                           size = 9, angle = 45, vjust = 1)) + theme(axis.title.x = element_text(vjust=1.9)) + theme(axis.text=element_text(size=9),
        axis.title=element_text(size=9,face="bold")) + theme(legend.text = element_text(size=9)) + theme(panel.border = element_rect(colour = "black", fill = NA, size =1)) + theme(legend.title = element_blank()) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"))
```


# Familiarity predicts Reaction Time

```{r}
m <- lmer( log(RT) ~ fam + ( fam | subID) + ( 1 | trait), data = fullTest)
summary(m)
ggpredict(m, c("fam")) %>% plot()
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
```

```{r}
m <- lmer( log(RT) ~ fam + propCorr + desirability + ( fam | subID) + ( 1 | trait), data = fullTest)
summary(m)
ggpredict(m, c("fam")) %>% plot()
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
```


# Replication of prior self-anchoring findings: Self-evaluations predicting ingroup evaluations

## No covariates

```{r}
m <- glmer( ingChoiceN ~ selfResp.Z +  ( selfResp.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
```


## Covariates

```{r}
m <- glmer( ingChoiceN ~ selfResp.Z + propCorr + desirability + ( selfResp.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
r2beta(m)
ggpredict(m, c("selfResp.Z")) %>% plot(show.title=F) + xlab("Self-Descriptiveness") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()
ggsave("~/Documents/UC Riverside/Studies/Self-Anchoring/Figures/SelfProjection.tiff",dpi=600)
```

# Does similarity-weighted self-evaluation average predict ingroup choices?

## No covariates

```{r}
m <- glmer( ingChoiceN ~ WSR.Z + ( WSR.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
```


## Covariates

```{r}
m <- glmer( ingChoiceN ~ WSR.Z + propCorr + desirability + ( WSR.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
r2beta(m)
```
# Does self-evaluation weighted similarity predict ingroup choices?

## No covariates

```{r}
m <- glmer( ingChoiceN ~ SE.Z + ( SE.Z | subID) , data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
```

## Covariates

```{r}
m <- glmer( ingChoiceN ~ SE.Z + propCorr + desirability + ( SE.Z | subID) , data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
r2beta(m)
```

# Do cross-validated similarity*self-evaluation predictions predict ingroup choices? 

## No covariates

```{r}
m <- glmer( ingChoiceN ~ predicted.Z + ( predicted.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
```

# Covariates

```{r}
m <- glmer( ingChoiceN ~ predicted.Z + propCorr + desirability + ( predicted.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
r2beta(m)
ggpredict(m, c("predicted.Z")) %>% plot(show.title=F) + xlab("Cross-Validated Self-Descriptiveness Predictions") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()
ggsave("~/Documents/UC Riverside/Studies/Self-Anchoring/Figures/CVprediction.tiff",dpi=600)
```
# Do people self-anchor more for higher indegree traits?

## No covariates

```{r}
m <- glmer( ingChoiceN ~ predicted.Z * inDegree + ( predicted.Z + inDegree | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
```

## Covariates

```{r}
m <- glmer( ingChoiceN ~ predicted.Z * inDegree + propCorr + desirability +  ( predicted.Z + inDegree | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("predicted.Z", "inDegree")) %>% plot(show.title=F) + xlab("Cross-Validated Self-Descriptiveness") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()
```


# Do people self-anchor more for higher outdegree traits?

## No covariates

```{r}
m <- glmer( ingChoiceN ~ predicted.Z * outDegree + ( predicted.Z + outDegree | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
```

## Covariates

```{r}
m <- glmer( ingChoiceN ~ predicted.Z * outDegree + propCorr + desirability +  ( predicted.Z + outDegree | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("predicted.Z", "outDegree")) %>% plot(show.title=F) + xlab("Cross-Validated Self-Descriptiveness") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()
```

# Do cross-validated similarity*self-evaluation predictions predict ingroup choices, regardless of whether it was seen prior or not?

## No covariates

```{r}
m <- glmer( ingChoiceN ~ predicted.Z * novel + ( predicted.Z + novel | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
```

## Covariates

```{r}
m <- glmer( ingChoiceN ~ predicted.Z * novel + propCorr + desirability + ( predicted.Z + novel | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
r2beta(m)
ggpredict(m, c("predicted.Z", "novel")) %>% plot(show.title=F)+ xlab("Cross-Validated Self-Descriptiveness") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()  + scale_color_discrete(labels = c("Trained","Held-Out"))
ggsave("~/Documents/UC Riverside/Studies/Self-Anchoring/Figures/CVpredictionGeneralize.tiff",dpi=600)
```

# Does generalization depend on outdegree?

## No covariates

```{r}
m <- glmer( ingChoiceN ~ predicted.Z * novel * outDegree  + ( predicted.Z + novel | subID) , data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
```

## Covariates

```{r}
m <- glmer( ingChoiceN ~ predicted.Z * novel * outDegree  + propCorr + desirability + ( predicted.Z + novel | subID) , data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
r2beta(m)
ggpredict(m, c("predicted.Z", "outDegree" ,"novel")) %>% plot(show.title=F)+ xlab("Cross-Validated Self-Descriptiveness") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()
ggsave("~/Documents/UC Riverside/Studies/Self-Anchoring/Figures/CVpredictionGeneralize.tiff",dpi=600)
```
# Does generalization depend on indegree?

## No covariates

```{r}
m <- glmer( ingChoiceN ~ predicted.Z * novel * inDegree + ( predicted.Z + novel | subID) , data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
```

## Covariates

```{r}
m <- glmer( ingChoiceN ~ predicted.Z * novel * inDegree + propCorr + desirability +  ( predicted.Z + novel | subID) , data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
r2beta(m)
ggpredict(m, c("predicted.Z", "outDegree" ,"novel")) %>% plot(show.title=F)+ xlab("Cross-Validated Self-Descriptiveness") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()
```

# Neighboring Dependencies Predicting Choices

## No covariates

```{r}
m <- glmer( ingChoiceN ~ neighAveOutSE.Z  + ( neighAveOutSE.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
```

## Covariates

```{r}
m <- glmer( ingChoiceN ~ neighAveOutSE.Z  + propCorr + desirability + ( neighAveOutSE.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
r2beta(m)
ggpredict(m, c("neighAveOutSE.Z")) %>% plot(show.title=F)+ xlab("Outwards Neighboring Self-Evaluations") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()
ggsave("~/Documents/UC Riverside/Studies/Self-Anchoring/Figures/outdegreeNeighbors.tiff",dpi=600)
```

# Generalization of Outdegree Neighboring Self-Evaluations

## No covariates

```{r}
m <- glmer( ingChoiceN ~ neighAveOutSE.Z * novel + ( neighAveOutSE.Z + novel | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
```

## Covariates

```{r}
m <- glmer( ingChoiceN ~ neighAveOutSE.Z * novel + propCorr + desirability + ( neighAveOutSE.Z + novel | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
r2beta(m)
ggpredict(m, c("neighAveOutSE.Z","novel")) %>% plot(show.title=F)+ xlab("Outwards Neighboring Self-Evaluations") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()
ggsave("~/Documents/UC Riverside/Studies/Self-Anchoring/Figures/outdegreeNeighborsGeneralization.tiff",dpi=600)
```

# Does entropy (i.e., uncertainty) predict likelihood of ingroup choices?

## No covariates

```{r}
m <- glmer( ingChoiceN ~ entropy.Z  + ( entropy.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
```

## Covariates

```{r}
m <- glmer( ingChoiceN ~ entropy.Z  + propCorr + desirability + ( entropy.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
r2beta(m)
ggpredict(m, c("entropy.Z")) %>% plot(show.title=F) + xlab("Uncertainty") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()
ggsave("~/Documents/UC Riverside/Studies/Self-Anchoring/Figures/Uncertainty.tiff",dpi=600)
```

# Does a linear trend of similarity-based probabilities predict ingroup choices?

## No covariates

```{r}
m <- glmer( ingChoiceN ~ slope.Z  + ( slope.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
```

## Covariates

```{r}
m <- glmer( ingChoiceN ~ slope.Z  + propCorr + desirability + ( slope.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
ggpredict(m, c("slope.Z")) %>% plot(show.title=F) + xlab("Linear Trend of Greater Self-Descriptiveness") + ylab("Likelihood of Ingroup Choice") + jtools::theme_apa()
ggsave("~/Documents/UC Riverside/Studies/Self-Anchoring/Figures/Slope.tiff",dpi=600)
```

# Does a linear trend of similarity-based probabilities predict ingroup choices, controlling for self-descriptiveness?

```{r}
m <- glmer( ingChoiceN ~ scale(slope) + selfResp.Z  + ( scale(slope) + selfResp.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
```

# Does a non-parametric trend of similarity-based probabilities predict ingroup choices, controlling for self-descriptiveness?

```{r}
m <- glmer( ingChoiceN ~ scale(nlslope) + selfResp.Z +  ( scale(nlslope) + selfResp.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
```

# Does a linear trend of similarity-based probabilities predict ingroup choices?

```{r}
m <- glmer( ingChoiceN ~ slope.Z  + predicted.Z + ( slope.Z + predicted.Z | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
```

# Backwards solution: Can you predict self-evaluations from similarity to ingroup and outgroup choices?

```{r}
m <- lmer( scale(selfResp) ~ scale(inGsim) + scale(outGsim) + (  scale(inGsim) + scale(outGsim) | subID) + (1 | trait), data = fullTrain)
summary(m)
tidy(m,conf.int=TRUE,effects="fixed")
ggpredict(m, c("inGsim")) %>% plot(show.title=F) + xlab("Similarity to Ingroup Choices") + ylab("Self-Evaluation") + jtools::theme_apa()
```

```{r}
m <- glmer( ingChoiceN ~ scale(slope) * novel  + ( scale(slope) + novel | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
```

```{r}
m <- glmer( ingChoiceN ~ eSE + ( eSE | subID) , data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
```


```{r}
m <- glmer( ingChoiceN ~ sSE + ( sSE | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
r2beta(m)
```

```{r}
m <- glmer( ingChoiceN ~ SE.Z * novel + ( SE.Z + novel | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
tidy(m,conf.int=TRUE,exponentiate=TRUE,effects="fixed")
r2beta(m)
```


```{r}
m <- glmer( as.factor(ingChoiceN) ~ SE.Z + scale(desirability) + ( SE.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)

m <- glmer( as.factor(ingChoiceN) ~ scale(oSE) + ( scale(oSE) | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)

m <- glmer( as.factor(ingChoiceN) ~ scale(iSE) + ( scale(iSE) | subID) + (1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)

m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel) + ( SE.Z + as.factor(novel) | subID) + (  1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)

m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel) + scale(desirability) + ( SE.Z + as.factor(novel) + scale(desirability) | subID) + (  1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("SE", "novel")) %>% plot()
```

```{r}
m <- glmer( as.factor(ingChoiceN) ~ predicted.Z*scale(RSE) + ( predicted.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("predicted.Z", "RSE")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ predicted.Z*scale(SCC) + ( predicted.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("predicted.Z", "SCC")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ predicted.Z*scale(DS) + ( predicted.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("predicted.Z", "DS")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ predicted.Z*scale(NFC) + ( predicted.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("predicted.Z", "NFC")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ predicted.Z*scale(SING.Ind) + ( predicted.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("predicted.Z", "SING.Ind")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ predicted.Z*scale(SING.Inter) + ( predicted.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("predicted.Z", "SING.Inter")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ predicted.Z*scale(Proto) + ( predicted.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("predicted.Z", "Proto")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ predicted.Z*scale(SI) + ( predicted.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("predicted.Z", "SI")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ predicted.Z*scale(NTB) + ( predicted.Z | subID) + ( predicted.Z | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("predicted.Z", "NTB")) %>% plot()
```

```{r}
m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(RSE) + ( entropy.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("entropy.Z", "RSE")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(SCC) + ( entropy.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("entropy.Z", "SCC")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(DS) + ( entropy.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("entropy.Z", "DS")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(NFC) + ( entropy.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("entropy.Z", "NFC")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(SING.Ind) + ( entropy.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("entropy.Z", "SING.Ind")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(SING.Inter) + ( entropy.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("entropy.Z", "SING.Inter")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(Proto) + ( entropy.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("entropy.Z", "Proto")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(SI) + ( entropy.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("entropy.Z", "SI")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ entropy.Z*scale(NTB) + ( entropy.Z | subID) + ( entropy.Z | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("entropy.Z", "NTB")) %>% plot()
```

```{r}
m <- glmer( as.factor(ingChoiceN) ~ slope.Z*scale(RSE) + ( slope.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("slope.Z", "RSE")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ slope.Z*scale(SCC) + ( slope.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("slope.Z", "SCC")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ slope.Z*scale(DS) + ( slope.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("slope.Z", "DS")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ slope.Z*scale(NFC) + ( slope.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("slope.Z", "NFC")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ slope.Z*scale(SING.Ind) + ( slope.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("slope.Z", "SING.Ind")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ slope.Z*scale(SING.Inter) + ( slope.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("slope.Z", "SING.Inter")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ slope.Z*scale(Proto) + ( slope.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("slope.Z", "Proto")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ slope.Z*scale(SI) + ( slope.Z | subID) + ( 1 | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("slope.Z", "SI")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ slope.Z*scale(NTB) + ( slope.Z | subID) + ( slope.Z | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("slope.Z", "NTB")) %>% plot()
```

```{r}
m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(RSE) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("desirability", "RSE")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(SCC) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("desirability", "SCC")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(DS) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("desirability", "DS")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(NFC) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("desirability", "NFC")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(SING.Ind) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("desirability", "SING.Ind")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(SING.Inter) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("desirability", "SING.Inter")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(Proto) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("desirability", "Proto")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(SI) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("desirability", "SI")) %>% plot()

m <- glmer( as.factor(ingChoiceN) ~ scale(desirability)*scale(NTB) + ( scale(desirability) | subID) + ( scale(desirability) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("desirability", "NTB")) %>% plot()
```

```{r}
m <- glmer( as.factor(ingChoiceN) ~ predicted.Z*novel*scale(NFC) + ( predicted.Z+novel | subID) + ( SE.Z*as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("SE", "novel","RSE")) %>% plot()
```

```{r}
m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel)*scale(SCC) + ( SE.Z+as.factor(novel) | subID) + ( SE.Z+as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("SE","novel","SCC")) %>% plot()
```

```{r}
m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel)*scale(DS) + ( SE.Z+as.factor(novel) | subID) + ( SE.Z+as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("SE","novel","DS")) %>% plot()
```

```{r}
m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel)*scale(NFC) + ( SE.Z+as.factor(novel) | subID) + ( SE.Z+as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("SE","novel", "NFC")) %>% plot()
```

```{r}
m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel)*scale(SING.Ind) + ( SE.Z+as.factor(novel) | subID) + ( SE.Z+as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("SE","novel","SING.Ind")) %>% plot()
```

```{r}
m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel)*scale(SING.Inter) + ( SE.Z+as.factor(novel) | subID) + ( SE.Z+as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("SE","novel","SING.Inter")) %>% plot()
```

```{r}
m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel)*scale(Proto) + ( SE.Z+as.factor(novel) | subID) + ( SE.Z+as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("SE", "Proto")) %>% plot()
```

```{r}
m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel)*scale(SI) + ( SE.Z+as.factor(novel) | subID) + ( SE.Z+as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("SE","novel","SI")) %>% plot()
```

```{r}
m <- glmer( as.factor(ingChoiceN) ~ SE.Z*as.factor(novel)*scale(NTB) + ( SE.Z+as.factor(novel) | subID) + ( SE.Z+as.factor(novel) | trait), data = fullTest, family = binomial, control = glmerControl(optimizer = "bobyqa",
                                    optCtrl = list(maxfun = 100000)),
    nAGQ = 1)
summary(m)
ggpredict(m, c("SE", "novel", "NTB")) %>% plot()
```


